uncbiag / easyreg Goto Github PK

https://github.com/uncbiag/mermaid can not be accessible without being a member of uncbiag. If mermaid is also going to be public, please ignore that.

It might be good to deploy a website to www.cs.unc.edu/{labname}/easyreg or anywhere that's possible. (The sphinx output)

Also, doc/ directory shouldn't be included in the final version, it just increases the download size.

Please, help me understand. How to use this source code and run step by step in order to have results? thank you.
I set up the environment completely.
** Which file can I run before?

Thank you very much.

The activation of easyreg is using the command conda, not source like a virtual enviroment.
The mistake is in the installation part.

I/O examples can be moved under demos folder.
(https://github.com/uncbiag/easyreg/tree/master/data_pre/examples)

The optional download demo operation requires gdown, yet the requirements are installed after that operation. Thus, the order of installation should be changed.

Files like .config, .idea, .vscode shouldn't be included in the repository. They should be on .gitignore

In the train_reg.py the name of the setting file for lpba is "cur_task_setting.json", however, in the folder it is "curr_task_setting.json". This is causing unexpected errors.

Paths like

https://github.com/uncbiag/easyreg/blob/master/settings/data_settings.json#L17

Shouldn't be set as a setting. User should be able to define such path via command line arguments or it should be indicated in the README.md file.

Zenodo enables creation of an open source scientific software citation, complete with a DOI. This enable recognition of the work and reproducibility through identification of computational dependencies.

An GitHub README badge with the citation that is automatically updated when a GitHub Release is created can be generated as documented here:

https://guides.github.com/activities/citable-code/

Many people are sharing BibTeX entries of the related papers to repository, so it might be worthful to follow that practice.

I am looking for Cross model image registration for some of my projects and I am wondering will it support cross-modal images.

I have attempted to run a demo for demons registration. How can I extract the resulting images of registration?

Thanks in advance.

I try to run ./demo/demo_for_easyreg_eval.py via python ./demo_for_easyreg_eval.py --setting_folder_path ./demo_settings/mermaid/opt_vsvf --gpu_id 0 --task_output_path ./demo_output/mermaid/
opt_vsvf -s ./image/image_1_save.nii.gz -t ./image/image_2_save.nii.gz.

However, the error had been occurred :
Traceback (most recent call last):
File "./demo_for_easyreg_eval.py", line 247, in
do_registration_eval(args, registration_pair_list, pair_name_list)
File "./demo_for_easyreg_eval.py", line 162, in do_registration_eval
run_one_task(tsm_json_path, dm_json_path)
File "D:\Python_Code\easyreg\easyreg\piplines.py", line 58, in run_one_task
pipline.initialize(task_setting_pth,data_setting_pth,data_loaders)
File "D:\Python_Code\easyreg\easyreg\piplines.py", line 28, in initialize
self.model = create_model(self.tsk_opt)
File "D:\Python_Code\easyreg\easyreg\create_model.py", line 29, in create_model
from .mermaid_iter import MermaidIter
File "D:\Python_Code\easyreg\easyreg\mermaid_iter.py", line 1, in
from .base_mermaid import MermaidBase
File "D:\Python_Code\easyreg\easyreg\base_mermaid.py", line 2, in
from .base_reg_model import RegModelBase
File "D:\Python_Code\easyreg\easyreg\base_reg_model.py", line 2, in
from .utils import *
File "D:\Python_Code\easyreg\easyreg\utils.py", line 7, in
import mermaid.image_sampling as py_is
ModuleNotFoundError: No module named 'mermaid'

Ana I can't found this file in this project.